Stability of Graph Neural Network with respect to different types of topological perturbations
A.R. Brown (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Elvin Isufi – Mentor (TU Delft - Multimedia Computing)
M. Sabbaqi – Mentor (TU Delft - Multimedia Computing)
Maosheng Yang – Mentor (TU Delft - Multimedia Computing)
K.A. Hildebrandt – Graduation committee member (TU Delft - Computer Graphics and Visualisation)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Graph Neural Networks are widely used as useful tools to investigate graphs because they can learn from the topological structure of graphs. In practical applications, the graph’s structure can change over time, have errors or be subject to adversarial attacks. These perturbations negatively impact the accuracy of the neural network. The theoretical stability of graph neural networks has been analysed already and in this paper, the stability of graph neural networks is investigated experimentally. The performance of different perturbation strategies is compared to see how different perturbations impact stability.